passdrill
AI & LLM Engineering · Building with LLM APIs · Card 010/012 easy

Some LLM APIs support returning `logprobs` (log probabilities) alongside generated text. What do these values represent, and what are they typically used for?

  1. They report how many milliseconds the API took to generate each token, and are used purely for latency monitoring and performance debugging
  2. They report, for each generated token, the log probability the model assigned to it (and often to alternative candidate tokens), and are typically used to gauge the model's confidence or build classifiers from token likelihoods
  3. They report the total dollar cost billed for each individual token, broken out on a per-token basis for detailed cost accounting
  4. They report which of several fine-tuned model versions actually generated each token, for use in auditing which checkpoint produced a given response
Next card → Shuffle